Subject Specific Sparse Dictionary Learning for Atlas Based Brain MRI Segmentation
|
|
- Prosper Lynch
- 5 years ago
- Views:
Transcription
1 Subject Specific Sparse Dictionary Learning for Atlas Based Brain MRI Segmentation Snehashis Roy 1,, Aaron Carass 2, Jerry L. Prince 2, and Dzung L. Pham 1 1 Center for Neuroscience and Regenerative Medicine, Henry Jackson Foundation 2 Department of Electrical and Computer Engineering, Johns Hopkins University Abstract. Quantitative measurements from segmentations of soft tissues from magnetic resonance images (MRI) of human brains provide important biomarkers for normal aging, as well as disease progression. In this paper, we propose a patch-based tissue classification method from MR images using sparse dictionary learning from an atlas. Unlike most atlas-based classification methods, deformable registration from the atlas to the subject is not required. An atlas consists of an MR image, its tissue probabilities, and the hard segmentation. The subject consists of the MR image and the corresponding affine registered atlas probabilities (or priors). A subject specific patch dictionary is created by learning relevant patches from the atlas. Then the subject patches are modeled as sparse combinations of learned atlas patches. The same sparse combination is applied to the segmentation patches of the atlas to generate tissue memberships of the subject. The novel combination of prior probabilities in the example patches enables us to distinguish tissues having similar intensities but having different spatial location. We show that our method outperforms two state-of-the-art whole brain tissue segmentation methods. We experimented on 12 subjects having manual tissue delineations, obtaining mean Dice coefficients of 0.91 and 0.87 for cortical gray matter and cerebral white matter, respectively. In addition, experiments on subjects with ventriculomegaly shows significantly better segmentation using our approach than the competing methods. Keywords: Image synthesis, intensity normalization, hallucination, patches. 1 Introduction Magnetic resonance imaging (MRI) is a widely used noninvasive modality to image the human brain. Postprocessing of MR images, such as tissue segmentation, provides quantitative biomarkers for understanding many aspects of normal aging, as well as progression and prognosis of diseases like Alzheimers disease and multiple sclerosis. Finite mixture models of the image intensity distributions is the basis of many image segmentation algorithms, where the intensity Support for this work included funding from the Department of Defense in the Center for Neuroscience and Regenerative Medicine and by the grants NIH/NINDS R01NS070906, NIH/NIBIB R21EB G. Wu et al. (Eds.): MLMI 2014, LNCS 8679, pp , Springer International Publishing Switzerland 2014
2 Subject Specific Sparse Dictionary Learning 249 histogram is fitted with a number of distributions, e.g. Gaussians, [1]. Other algorithms model the tissue intensities using fuzzy C-means (FCM) [2], partial volume models [3] etc. Prior information on the spatial locations of the tissue are usually incorporated using statistical atlases [4,2], which captures their spatial variability. Since there is no tissue-dependent global MR image intensity scale (unlike computed tomography), the intensity range and distribution varies significantly across scanners and imaging protocols. Thus it is sometimes unclear if a particular model is optimal for MR images with different acquisition protocols. Instead of trying to fit image intensities into pre-defined models, we rely on similar looking examples from expert segmented images. In this paper, we propose an example based brain segmentation method, combining statistical atlas priors into sparse dictionary learning. The atlas comprises an MR image, corresponding stastistical priors, and the hard segmentation into tissue labels, e.g, cerebral gray matter(gm), cerebral white matter (WM), ventricles, cerebro-spinal fluid (CSF) etc. An image patch from the subject MR along with the corresponding patches from the affine registered statistical priors in the subject space, comprise of an image feature. A sparse patch dictionary is learnt using the atlas and subject image features. For every subject patch, its sparse weight is found from the learnt dictionary. Corresponding atlas hard segmentation labels are weighted by the same weights to generate the tissue membership of the subject patch. In a previous example based binary segmentation method [5], prior information about spatial location of a tissue is obtained from a deformable registration of the atlas to the subject image. A binary dictionary-based labeling method was proposed for hippocampal segmetation in [6]. Our method is similar in concept to this approach, but we perform whole brain segmentation using a single dictionary encompassing multiple tissue classes using statistical priors without the need for deformable registration between subject and atlas. Since the previous example based methods [5,6] are only applicable to binary segmentation, we compare our method with two state-of-the-art publicly available whole brain multi-class segmentation methods, Freesurfer [3] and TOADS [2], and show that segmentation accuracy significantly improves with our example based method. We also experimented on 10 subjects with ventriculomegaly and show that when the anatomy between atlas and subject is significantly different (e.g., enlarged ventricles), our method is more robust. 2 Method We define an atlas as a (n+1)-tuple of images, {a 1,...,a n+1 },wherea 1 denotes the T 1 -w MR scan, a n+1 denotes the hard segmentation, and a 2 a n denotes (n 1) statistical priors. At each voxel, a 3D patch can be defined on every atlas image and are rasterized as a d 1 vector a k (i), where i =1,...,M,isan index over the voxels of the atlas. A subject MR image is denoted by s 1.Atlas a 1 is affine registered to s 1,andthepriorsa 2 a n are transformed to the subject space by the same affine transformation. The transformed priors are denoted by {s 2,...,s n }. The subject patches are denoted by s k (j), j =1,...,N. The idea is
3 250 S. Roy et al. to use these images {a 1,...,a n+1,s 1,...,s n } to generate a segmentation ŝ n+1. The priors can be weighted, i.e., s k w s k,wherew is a scalar multiplying the prior images. An atlas patch dictionary is defined as A 1 R nd M, where the i th column of A 1, f(i), consists of the ordered concatenation of atlas patches (a k (i)), i.e., f(i) =[a 1 (i) T...a n (i) T ] T.Thusthend 1 vectors f(i) becomes the atlas feature vectors. Similarly, the subject feature vectors are denoted by b(j) = [s 1 (i) T...s n (i) T ] T, b(j) R nd. We also refer to the nd 1 feature vector as a patch. A patch encodes the intensity information of a voxel and its neighborhood, as well as its spatial information via the use of statistical atlases. The atlas segmentation image is also decomposed into patches a n+1 (i), which forms the columns of the segmentation dictionary A Sparse Dictionary Learning If the atlas and the subjects have similar tissue contrasts, we can assume that for every subject patch s 1 (j), a small number of similar looking patches can always be found from the set of atlas patches (a 1 (i)) [7,8]. We extend this assumption for the nd 1 feature vectors b(j) as well, enforcing the condition that every subject feature can be matched to a few atlas feature vectors, having not only similar intensities but similar spatial locations as well. This idea of sparse matching can be written as b(j) A 1 x(j), for some x(j) R M, x(j) 0 M, j. (1) Previous methods [6,5] try to enforce the similarity in spatial locations by searching for the similar patches in a small window around the j th voxel. We obviate the need for such windowed searching by adding statistical priors in the features. The non-negativity constraints in the weight x(j) enforces the similarity in texture between the subject patch and the chosen atlas patches. The combinatorics of the l 0 problem in Eqn. 1 makes it infeasible to solve directly, but it can be transformed into an l 1 minimization problem, { ˆx(j) =argmin b(j) A1 x(j) 2 } 2 + λ x(j) 1, subject to f(i) 2 2 =1 (2) x 0 However, x(j) isam 1 vector, where M is the number of atlas patches, typically M Thus solving such a large optimization for every subject patch is computationally intensive. We use sparse dictionary learning to generate a dictionary of smaller length D 1 R nd L,fromA 1, which can be used instead of A 1 ineqn.2tosolveforx(j). We have chosen L = 5000 empirically. The advantage of learning a dictionary is twofold. First, although the dictionary elements are not orthogonal, all the subject patches (b(j)) can be sparsely represented using the dictionary elements. Second, the computational burden of Eqn. 2 for every subject patch is reduced. The sparse dictionary is learnt using training examples from the subject such that all subject patches can be optimally represented via the dictionary [9]. The dictionary learning approach is an alternating minimization to solve the following problem, {ˆx(j), ˆD1 } =argmin x 0,D 1 N { b(j) D1 x(j) 2 } 2 + λ x(j) 1, s.t f(i) 2 2 =1. (3) j=1
4 Subject Specific Sparse Dictionary Learning 251 Initial Dictionary Final Dictionary Fig. 1. The left image shows middle sections of 100 randomly chosen 3 3 3patches from D (0) 1, while on the right are the same atlas patches learnt from the subject after five iterations of Eqn. 5 f(i),i=1...,m are the columns of D 1. Eqn. 3 can be solved in two alternating steps. First, keeping D 1 fixed, we solve for x(j) foreachj, asineqn.2.then keeping x(j) fixed, we solve N ˆD 1 =argmin b(j) D 1 x(j) 2 2. (4) D 1 j=1 A gradient descent approach leads to the following update equation, D (t+1) 1 = D (t) 1 + η N (b(j) D (t) 1 x(j))x(j)t, (5) j=1 where η is the step-size and t denotes iteration numbers. We note that η should be chosen carefully so that D (t) 1 > 0 always, since the columns of D 1 contains MR intensities and statistical priors. D (0) 1 is generated using L randomly chosen columns of A 1. The segmentation dictionary D 2 is generated using corresponding columns of A 2. Once the dictionary is learnt after the convergence of Eqn. 5, Eqn. 2 is solved for every subject patch b(j) using ˆD 1 instead of A 1, to find the sparse representation x(j). Every atlas patch in the learnt dictionary D 1 has a corresponding segmentation patch in D 2.ThusthecolumnsofD 2 contain segmentation labels {2,...,k}. Itcanbeshownthat x(j) 1 follows a Laplace distribution with mean 1. Empirically, the variance is found to be very small ( 0.005). Thus we weigh the segmentation labels according to their weights in x(j) to generate tissue memberships, x(j) p k =(1 D2 (k)),k =2,...,n, (6) x(j) 1 where 1 D2 (k) denotes the indicator matrix having the same size as D 2,whose elements are 1 if the corresponding element in D 2 is k, 0otherwise.k =2,...,n denotes (n 1) tissue labels. We only take the central voxel of p k to generate the full membership image p k.
5 252 S. Roy et al. 2.2 Updating Statistical Priors in the Segmentation We have described a method to obtain tissue memberships from a set of MR images and statistical priors. Usually, fixed statistical priors should be non-zero and fuzzy, leaving a possibility that a CSF patch can be matched to a ventricle patch, which have similar intensity as well as similar prior. On the other hand, less fuzzy priors will introduce too much dependence on the accurate initial alignment between the atlas and the subject. Instead of using a fixed prior based on the initial atlas-to-subject registration, we dynamically update it by iterating the same patch selection method stated above. The statistical priors ({s 2,...,s n }) at each iteration is replaced by a Gaussian blurred version of the obtained memberships p k [10]. The blurring relaxes the localization of the tissues in the memberships by increasing the capture range in the priors. The algorithm can be written as, 1. At t = 0, start with {a 1,...,a n+1,s 1,s (0) 2...,s (0) n }, wheres (0) k are the registered atlas priors, k =2,...,n. 2. Generate dictionaries ˆD 1 and D 2 from Eqn. 5 using {a 1,...,a n+1,s 1,s (0) 2..., s (0) n }. The subject patches are denoted by b (0) (j). 3. At t t + 1, for each subject patch b (t) (j), generate the sparse coefficient x (t) (j) using ˆD 1 from Eqn Generate memberships {p (t) 2,...,p(t) n } using x (t) (j)s from Eqn Generate new statistical priors s (t) k G σ p (t) k,k =2,...,n. σ =3mmis chosen empirically. 6. Generate b (t+1) (j) usingthenew{s 1,s (t) 2,...,s(t) n } 1 N 7. Stop if N j=1 x(t) (j) x (t 1) (j) <ɛ,elsegotostep3. 3 Results. Clearly, after learning from the subject patches, there are more edges in D (5) 1 patches, compared to the flat -looking patches in D (0) 1, indicating The run-time is approximately ½hours on 2.7GHz 12-core AMD processors for sized 1mm 3 images. SparseLab is used to solve Eqn. 2. We used patches in all our experiments, and empirically chose the atlas weight w as λ for Eqn. 2 and η for Eqn. 5 are chosen as 0.01 and 0.001, respectively. All images are skull-stripped [11] and corrected for any intensity inhomogeneity [12]. All MR images are intensity normalized so that their modes of WM intensities are unity [13]. WM intensity modes are found by fitting a smooth kernel density estimator to the histograms. An example of the learnt dictionary is shown in Fig. 1, where D (0) 1 is compared with D (5) 1 D (5) 1 can represent any unknown subject patch better than D (0) 1.Fig.2shows the effect of iteratively updating the priors via memberships. Since the atlas is registered to the subject using affine only, the strong GM prior in the middle of WM (red arrow) introduces non-zero membership to the WM patches. However, the dynamic prior update at each iteration, instead of a fixed prior in most EM based algorithms, reduces the dependence.
6 Subject Specific Sparse Dictionary Learning 253 Atlas Ventricle GM WM Subject MR Iter 1 Iter 5 Segmentation Fig. 2. Top row shows affine registered atlas images, registered to the subject in the bottom row. WM memberships (p k )forthe1 st and 5 th iteration of the algorithm (Sec. 2.2) are also shown. The last column shows the max-membership hard segmentation output of our method. We validated on 12 subjects from CUMC12 database [14], which have manually segmented labels. The manual segmentations do not have any CSF. We segment the images into 4 classes, GM, WM, ventricle and subcortical GM (e.g., caudate, putamen, thalamus). One subject is randomly chosen as atlas. Since they do not have any tissue probability or memberships, Gaussian blurred tissue label-masks (σ = 3mm) are used as priors {a 2,...,a n }. The remaining 11 subjects are segmented using the atlas MR and priors. Dice coefficients comparing three methods on the four tissue classes, as well as the weighted average (W. Ave.) of the four, weighted by the volume of the corresponding tissue, are shown in Table 1. Our method outperforms the other two methods in GM, WM, subcortical GM and in the average (p <0.05 in all cases). Since the ventricle boundary is usually the most robust feature in an MR image, all three methods perform similarly. NPH Subject TOADS Freesurfer Dictionary Manual Fig. 3. A subject with NPH is segmented using TOADS, Freesurfer and our dictionary learning method. Rightmost column shows manual delineation of the ventricles.
7 254 S. Roy et al. Table 1. Mean Dice coefficients for four tissue types and their weighted average, averaged over 11 subjects from CUMC12 database are shown Ventricle GM Subcort. GM WM W. Ave. TOADS ± ± ± ± ±0.011 Freesurfer ± ± ± ± ±0.009 Dictionary 0.785± ± ± ± ±0.008 bold indicates statistically significantly larger than the other two (p <0.05). Fig. 4. Dice coefficients of between manual ventricle delineation and three automatic methods are shown for 10 subjects with NPH Next we applied the dictionary learning algorithm on 10 subjects with normal pressure hydrocephalus (NPH), which have enlarged ventricles. Manual segmentations are available only on ventricles. They are segmented with Freesurfer using the -bigventricles flag. Fig. 3 shows one subject with the segmentations and the manual delineation of the ventricles. The atlas is shown in Fig. 2. In this case, 7 tissue classes, cerebellar GM, cerebellar WM, cerebral GM and WM, subcortical GM, CSF and ventricles, are used. Clearly, our method significantly improves the ventricle segmentation. Freesurfer segments part of the ventricles as WM and lesions (red arrow), while TOADS segments part of it as cortical GM. Visually, our method produces better CSF segmentation as well (green arrow). Quantitative improvement is shown in Fig. 4 where Dice coefficients between manually segmented ventricles and automatic segmentations are plotted for the three methods. Our method produces the most consistent Dice coefficient (mean 0.91) across all subjects with very little variance, and it is significantly (p <0.05) larger than TOADS (mean Dice 0.71) and Freesurfer (mean Dice 0.72). Although we used default settings for TOADS or Freesurfer, no amount of parameter tuning would significantly improve the NPH results. 4 Discussion We have presented a patch based sparse dictionary learning method to segment multiple tissue classes. Contrary to previous binary patch based segmentation
8 Subject Specific Sparse Dictionary Learning 255 methods, we use statistical priors to localize different tissues with similar intensities. We do not require any deformable registration of the subject to the atlas. References 1. Ashburner, J., Friston, K.J.: Unified segmentation. NeuroImage 26(3), (2005) 2. Shiee, N., Bazin, P., Ozturk, A., Reich, D.S., Calabresi, P.A., Pham, D.L.: A Topology-Preserving Approach to the Segmentation of Brain Images with Multiple Sclerosis Lesions. NeuroImage (2009) 3. Dale, A.M., Fischl, B., Sereno, M.I.: Cortical Surface-Based Analysis I: Segmentation and Surface Reconstruction. NeuroImage 9(2), (1999) 4. Leemput, K.V., Maes, F., Vandermeulen, D., Suetens, P.: Automated Model- Based Tissue Classification of MR Images of the Brain. IEEE Trans. on Med. Imag. 18(10), (1999) 5. Coupé, P., Eskildsen, S.F., Manjón, J.V., Fonov, V.S., Collins, D.L.: The Alzheimer s disease Neuroimaging Initiative: Simultaneous segmentation and grading of anatomical structures for patient s classification: application to Alzheimer s disease. NeuroImage 59(4), (2012) 6. Tong, T., Wolz, R., Coupe, P., Hajnal, J.V., Rueckert, D.: The Alzheimer s Disease Neuroimaging Initiative: Segmentation of MR images via discriminative dictionary learning and sparse coding: Application to hippocampus labeling. NeuroImage 76(1), (2013) 7. Roy, S., Carass, A., Prince, J.: Magnetic Resonance Image Example Based Contrast Synthesis. IEEE Trans. Med. Imag. 32(12), (2013) 8. Cao, T., Zach, C., Modla, S., Powell, D., Czymmek, K., Niethammer, M.: Registration for correlative microscopy using image analogies. In: Dawant, B.M., Christensen, G.E., Fitzpatrick, J.M., Rueckert, D. (eds.) WBIR LNCS, vol. 7359, pp Springer, Heidelberg (2012) 9. Aharon, M., Elad, M., Bruckstein, A.M.: K-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation. IEEE Trans. Sig. Proc. 54(11), (2006) 10. Shiee, N., Bazin, P.-L., Cuzzocreo, J.L., Blitz, A., Pham, D.L.: Segmentation of brain images using adaptive atlases with application to ventriculomegaly. In: Székely, G., Hahn, H.K. (eds.) IPMI LNCS, vol. 6801, pp Springer, Heidelberg (2011) 11. Carass, A., Cuzzocreo, J., Wheeler, M.B., Bazin, P.L., Resnick, S.M., Prince, J.L.: Simple paradigm for extra-cerebral tissue removal: Algorithm and analysis. NeuroImage 56(4), (2011) 12. Sled, J.G., Zijdenbos, A.P., Evans, A.C.: A non-parametric method for automatic correction of intensity non-uniformity in MRI data. IEEE Trans. on Med. Imag. 17(1), (1998) 13. Pham, D.L., Prince, J.L.: An Adaptive Fuzzy C-Means Algorithm for Image Segmentation in the Presence of Intensity Inhomogeneities. Pattern Recog. Letters 20(1), (1999) 14. Klein, A., et al.: Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration. NeuroImage 46(3), (2009)
MR Brain Segmentation using Decision Trees
MR Brain Segmentation using Decision Trees Amod Jog, Snehashis Roy, Jerry L. Prince, and Aaron Carass Image Analysis and Communication Laboratory, Dept. of Electrical and Computer Engineering, The Johns
More informationNIH Public Access Author Manuscript Proc SPIE. Author manuscript; available in PMC 2013 December 30.
NIH Public Access Author Manuscript Published in final edited form as: Proc SPIE. 2013 March 12; 8669:. doi:10.1117/12.2006682. Longitudinal Intensity Normalization of Magnetic Resonance Images using Patches
More informationMedical Image Synthesis Methods and Applications
MR Intensity Scale is Arbitrary This causes problems in most postprocessing methods Inconsistency or algorithm failure 11/5/2015 2 Joint Histogram 1.5 T GE SPGR 3 T Philips MPRAGE 11/5/2015 3 Problem With
More informationAn Introduction To Automatic Tissue Classification Of Brain MRI. Colm Elliott Mar 2014
An Introduction To Automatic Tissue Classification Of Brain MRI Colm Elliott Mar 2014 Tissue Classification Tissue classification is part of many processing pipelines. We often want to classify each voxel
More informationDistance Transforms in Multi Channel MR Image Registration
Distance Transforms in Multi Channel MR Image Registration Min Chen 1, Aaron Carass 1, John Bogovic 1, Pierre-Louis Bazin 2 and Jerry L. Prince 1 1 Image Analysis and Communications Laboratory, 2 The Laboratory
More informationAutomatic segmentation of the cortical grey and white matter in MRI using a Region Growing approach based on anatomical knowledge
Automatic segmentation of the cortical grey and white matter in MRI using a Region Growing approach based on anatomical knowledge Christian Wasserthal 1, Karin Engel 1, Karsten Rink 1 und André Brechmann
More informationNIH Public Access Author Manuscript Proc SPIE. Author manuscript; available in PMC 2013 December 31.
NIH Public Access Author Manuscript Published in final edited form as: Proc SPIE. 2013 March 3; 8669:. doi:10.1117/12.2007062. Pulse Sequence based Multi-acquisition MR Intensity Normalization Amod Jog,
More informationNeuroimaging and mathematical modelling Lesson 2: Voxel Based Morphometry
Neuroimaging and mathematical modelling Lesson 2: Voxel Based Morphometry Nivedita Agarwal, MD Nivedita.agarwal@apss.tn.it Nivedita.agarwal@unitn.it Volume and surface morphometry Brain volume White matter
More informationTopology Preserving Brain Tissue Segmentation Using Graph Cuts
Topology Preserving Brain Tissue Segmentation Using Graph Cuts Xinyang Liu 1, Pierre-Louis Bazin 2, Aaron Carass 3, and Jerry Prince 3 1 Brigham and Women s Hospital, Boston, MA 1 xinyang@bwh.harvard.edu
More informationModified Expectation Maximization Method for Automatic Segmentation of MR Brain Images
Modified Expectation Maximization Method for Automatic Segmentation of MR Brain Images R.Meena Prakash, R.Shantha Selva Kumari 1 P.S.R.Engineering College, Sivakasi, Tamil Nadu, India 2 Mepco Schlenk Engineering
More informationAutomatic Generation of Training Data for Brain Tissue Classification from MRI
MICCAI-2002 1 Automatic Generation of Training Data for Brain Tissue Classification from MRI Chris A. Cocosco, Alex P. Zijdenbos, and Alan C. Evans McConnell Brain Imaging Centre, Montreal Neurological
More informationMethods for data preprocessing
Methods for data preprocessing John Ashburner Wellcome Trust Centre for Neuroimaging, 12 Queen Square, London, UK. Overview Voxel-Based Morphometry Morphometry in general Volumetrics VBM preprocessing
More informationSegmentation of Brain MR Images via Sparse Patch Representation
Segmentation of Brain MR Images via Sparse Patch Representation Tong Tong 1, Robin Wolz 1, Joseph V. Hajnal 2, and Daniel Rueckert 1 1 Department of Computing, Imperial College London, London, UK 2 MRC
More informationIs Synthesizing MRI Contrast Useful for Inter-modality Analysis?
Is Synthesizing MRI Contrast Useful for Inter-modality Analysis? Juan Eugenio Iglesias 1, Ender Konukoglu 1, Darko Zikic 2, Ben Glocker 2, Koen Van Leemput 1,3,4 and Bruce Fischl 1 1 Martinos Center for
More informationPreprocessing II: Between Subjects John Ashburner
Preprocessing II: Between Subjects John Ashburner Pre-processing Overview Statistics or whatever fmri time-series Anatomical MRI Template Smoothed Estimate Spatial Norm Motion Correct Smooth Coregister
More informationMulti-atlas labeling with population-specific template and non-local patch-based label fusion
Multi-atlas labeling with population-specific template and non-local patch-based label fusion Vladimir Fonov, Pierrick Coupé, Simon Eskildsen, Jose Manjon, Louis Collins To cite this version: Vladimir
More informationEnsemble registration: Combining groupwise registration and segmentation
PURWANI, COOTES, TWINING: ENSEMBLE REGISTRATION 1 Ensemble registration: Combining groupwise registration and segmentation Sri Purwani 1,2 sri.purwani@postgrad.manchester.ac.uk Tim Cootes 1 t.cootes@manchester.ac.uk
More informationAutomatic Registration-Based Segmentation for Neonatal Brains Using ANTs and Atropos
Automatic Registration-Based Segmentation for Neonatal Brains Using ANTs and Atropos Jue Wu and Brian Avants Penn Image Computing and Science Lab, University of Pennsylvania, Philadelphia, USA Abstract.
More informationNIH Public Access Author Manuscript Inf Process Med Imaging. Author manuscript; available in PMC 2012 July 17.
NIH Public Access Author Manuscript Published in final edited form as: Inf Process Med Imaging. 2011 ; 22: 371 383. A Compressed Sensing Approach for MR Tissue Contrast Synthesis Snehashis Roy, Aaron Carass,
More informationSegmenting Glioma in Multi-Modal Images using a Generative Model for Brain Lesion Segmentation
Segmenting Glioma in Multi-Modal Images using a Generative Model for Brain Lesion Segmentation Bjoern H. Menze 1,2, Koen Van Leemput 3, Danial Lashkari 4 Marc-André Weber 5, Nicholas Ayache 2, and Polina
More informationMAGNETIC resonance (MR) imaging (MRI) is widely
2348 IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 32, NO. 12, DECEMBER 2013 Magnetic Resonance Image Example-Based Contrast Synthesis Snehashis Roy, StudentMember,IEEE,AaronCarass*, Member, IEEE, and Jerry
More informationAutomatic Generation of Training Data for Brain Tissue Classification from MRI
Automatic Generation of Training Data for Brain Tissue Classification from MRI Chris A. COCOSCO, Alex P. ZIJDENBOS, and Alan C. EVANS http://www.bic.mni.mcgill.ca/users/crisco/ McConnell Brain Imaging
More informationKnowledge-Based Segmentation of Brain MRI Scans Using the Insight Toolkit
Knowledge-Based Segmentation of Brain MRI Scans Using the Insight Toolkit John Melonakos 1, Ramsey Al-Hakim 1, James Fallon 2 and Allen Tannenbaum 1 1 Georgia Institute of Technology, Atlanta GA 30332,
More informationPerformance Evaluation of the TINA Medical Image Segmentation Algorithm on Brainweb Simulated Images
Tina Memo No. 2008-003 Internal Memo Performance Evaluation of the TINA Medical Image Segmentation Algorithm on Brainweb Simulated Images P. A. Bromiley Last updated 20 / 12 / 2007 Imaging Science and
More informationMARS: Multiple Atlases Robust Segmentation
Software Release (1.0.1) Last updated: April 30, 2014. MARS: Multiple Atlases Robust Segmentation Guorong Wu, Minjeong Kim, Gerard Sanroma, and Dinggang Shen {grwu, mjkim, gerard_sanroma, dgshen}@med.unc.edu
More informationSUPER RESOLUTION RECONSTRUCTION OF CARDIAC MRI USING COUPLED DICTIONARY LEARNING
SUPER RESOLUTION RECONSTRUCTION OF CARDIAC MRI USING COUPLED DICTIONARY LEARNING Abstract M. Vinod Kumar (M.tech) 1 V. Gurumurthy Associate Professor, M.Tech (Ph.D) 2 Dr.M. Narayana, Professor, Head of
More informationSimultaneous Cortical Surface Labeling and Sulcal Curve Extraction
Simultaneous Cortical Surface Labeling and Sulcal Curve Extraction Zhen Yang a, Aaron Carass a, Chen Chen a, Jerry L Prince a,b a Electrical and Computer Engineering, b Biomedical Engineering, Johns Hopkins
More informationAutomated Brain-Tissue Segmentation by Multi-Feature SVM Classification
Automated Brain-Tissue Segmentation by Multi-Feature SVM Classification Annegreet van Opbroek 1, Fedde van der Lijn 1 and Marleen de Bruijne 1,2 1 Biomedical Imaging Group Rotterdam, Departments of Medical
More informationIschemic Stroke Lesion Segmentation Proceedings 5th October 2015 Munich, Germany
0111010001110001101000100101010111100111011100100011011101110101101012 Ischemic Stroke Lesion Segmentation www.isles-challenge.org Proceedings 5th October 2015 Munich, Germany Preface Stroke is the second
More informationAutomatic MS Lesion Segmentation by Outlier Detection and Information Theoretic Region Partitioning Release 0.00
Automatic MS Lesion Segmentation by Outlier Detection and Information Theoretic Region Partitioning Release 0.00 Marcel Prastawa 1 and Guido Gerig 1 Abstract July 17, 2008 1 Scientific Computing and Imaging
More informationLilla Zöllei A.A. Martinos Center, MGH; Boston, MA
Lilla Zöllei lzollei@nmr.mgh.harvard.edu A.A. Martinos Center, MGH; Boston, MA Bruce Fischl Gheorghe Postelnicu Jean Augustinack Anastasia Yendiki Allison Stevens Kristen Huber Sita Kakonoori + the FreeSurfer
More informationSegmenting Glioma in Multi-Modal Images using a Generative-Discriminative Model for Brain Lesion Segmentation
Segmenting Glioma in Multi-Modal Images using a Generative-Discriminative Model for Brain Lesion Segmentation Bjoern H. Menze 1,2, Ezequiel Geremia 2, Nicholas Ayache 2, and Gabor Szekely 1 1 Computer
More informationSUPER-RESOLUTION RECONSTRUCTION ALGORITHM FOR BASED ON COUPLED DICTIONARY LEARNING CARDIAC MRI RECONSTRUCTION
SUPER-RESOLUTION RECONSTRUCTION ALGORITHM FOR BASED ON COUPLED DICTIONARY LEARNING CARDIAC MRI RECONSTRUCTION M.PRATHAP KUMAR, Email Id: Prathap.Macherla@Gmail.Com J.VENKATA LAKSHMI, M.Tech, Asst.Prof,
More informationNorbert Schuff VA Medical Center and UCSF
Norbert Schuff Medical Center and UCSF Norbert.schuff@ucsf.edu Medical Imaging Informatics N.Schuff Course # 170.03 Slide 1/67 Objective Learn the principle segmentation techniques Understand the role
More informationA Review on Label Image Constrained Multiatlas Selection
A Review on Label Image Constrained Multiatlas Selection Ms. VAIBHAVI NANDKUMAR JAGTAP 1, Mr. SANTOSH D. KALE 2 1PG Scholar, Department of Electronics and Telecommunication, SVPM College of Engineering,
More informationPBSI: A symmetric probabilistic extension of the Boundary Shift Integral
PBSI: A symmetric probabilistic extension of the Boundary Shift Integral Christian Ledig 1, Robin Wolz 1, Paul Aljabar 1,2, Jyrki Lötjönen 3, Daniel Rueckert 1 1 Department of Computing, Imperial College
More informationOptimized Super Resolution Reconstruction Framework for Cardiac MRI Images Perception
Optimized Super Resolution Reconstruction Framework for Cardiac MRI Images Perception 1 P.Hari Prasad, 2 N. Suresh, 3 S. Koteswara Rao 1 Asist, Decs, JNTU Kakinada, Vijayawada, Krishna (Dist), Andhra Pradesh
More informationWhere are we now? Structural MRI processing and analysis
Where are we now? Structural MRI processing and analysis Pierre-Louis Bazin bazin@cbs.mpg.de Leipzig, Germany Structural MRI processing: why bother? Just use the standards? SPM FreeSurfer FSL However:
More informationKnowledge-Based Segmentation of Brain MRI Scans Using the Insight Toolkit
Knowledge-Based Segmentation of Brain MRI Scans Using the Insight Toolkit John Melonakos 1, Ramsey Al-Hakim 1, James Fallon 2 and Allen Tannenbaum 1 1 Georgia Institute of Technology, Atlanta GA 30332,
More informationSuper-Resolution Rebuilding Of Cardiac MRI Using Coupled Dictionary Analyzing
Super-Resolution Rebuilding Of Cardiac MRI Using Coupled Dictionary Analyzing VALLAKATI MADHAVI 1 CE&SP (ECE) Osmania University, HYDERABAD chittymadhavi92@gmail.com MRS.SHOBA REDDY 2 P.HD OsmaniaUniversity,
More informationMR IMAGE SEGMENTATION
MR IMAGE SEGMENTATION Prepared by : Monil Shah What is Segmentation? Partitioning a region or regions of interest in images such that each region corresponds to one or more anatomic structures Classification
More informationDiscriminative, Semantic Segmentation of Brain Tissue in MR Images
Discriminative, Semantic Segmentation of Brain Tissue in MR Images Zhao Yi 1, Antonio Criminisi 2, Jamie Shotton 2, and Andrew Blake 2 1 University of California, Los Angeles, USA. zyi@ucla.edu. 2 Microsoft
More informationProcessing math: 100% Intensity Normalization
Intensity Normalization Overall Pipeline 2/21 Intensity normalization Conventional MRI intensites (T1-w, T2-w, PD, FLAIR) are acquired in arbitrary units Images are not comparable across scanners, subjects,
More informationLOCUS: LOcal Cooperative Unified Segmentation of MRI Brain Scans
Author manuscript, published in "MICCAI07-10th International Conference on Medical Image Computing and Computer Assisted Intervention, Brisbane : Australia (2007)" DOI : 10.1007/978-3-540-75757-3_27 LOCUS:
More informationDetecting Changes In Non-Isotropic Images
Detecting Changes In Non-Isotropic Images K.J. Worsley 1, M. Andermann 1, T. Koulis 1, D. MacDonald, 2 and A.C. Evans 2 August 4, 1999 1 Department of Mathematics and Statistics, 2 Montreal Neurological
More informationTHE identification and delineation of brain structures from
IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 26, NO. 4, APRIL 2007 479 Atlas Renormalization for Improved Brain MR Image Segmentation Across Scanner Platforms Xiao Han and Bruce Fischl* Abstract Atlas-based
More informationMeasuring longitudinal brain changes in humans and small animal models. Christos Davatzikos
Measuring longitudinal brain changes in humans and small animal models Christos Davatzikos Section of Biomedical Image Analysis University of Pennsylvania (Radiology) http://www.rad.upenn.edu/sbia Computational
More informationPROSTATE CANCER DETECTION USING LABEL IMAGE CONSTRAINED MULTIATLAS SELECTION
PROSTATE CANCER DETECTION USING LABEL IMAGE CONSTRAINED MULTIATLAS SELECTION Ms. Vaibhavi Nandkumar Jagtap 1, Mr. Santosh D. Kale 2 1 PG Scholar, 2 Assistant Professor, Department of Electronics and Telecommunication,
More informationAN AUTOMATED SEGMENTATION FRAMEWORK FOR BRAIN MRI VOLUMES BASED ON ADAPTIVE MEAN-SHIFT CLUSTERING
AN AUTOMATED SEGMENTATION FRAMEWORK FOR BRAIN MRI VOLUMES BASED ON ADAPTIVE MEAN-SHIFT CLUSTERING Sam Ponnachan 1, Paul Pandi 2,A.Winifred 3,Joselin Jose 4 UG Scholars 1,2,3,4 Department of EIE 1,2 Department
More informationLearning Algorithms for Medical Image Analysis. Matteo Santoro slipguru
Learning Algorithms for Medical Image Analysis Matteo Santoro slipguru santoro@disi.unige.it June 8, 2010 Outline 1. learning-based strategies for quantitative image analysis 2. automatic annotation of
More informationGround Truth Estimation by Maximizing Topological Agreements in Electron Microscopy Data
Ground Truth Estimation by Maximizing Topological Agreements in Electron Microscopy Data Huei-Fang Yang and Yoonsuck Choe Department of Computer Science and Engineering Texas A&M University College Station,
More informationPatch Based Synthesis of Whole Head MR Images: Application To EPI Distortion Correction
Patch Based Synthesis of Whole Head MR Images: Application To EPI Distortion Correction Snehashis Roy 1(B), Yi-Yu Chou 1, Amod Jog 2, John A. Butman 3, and Dzung L. Pham 1 1 Center for Neuroscience and
More informationSuper-resolved Multi-channel Fuzzy Segmentation of MR Brain Images
Super-resolved Multi-channel Fuzzy Segmentation of MR Brain Images Ying Bai a,xiaohan a, Dzung L. Pham b, and Jerry L. Prince a a Image Analysis and Communication Laboratory, Johns Hopkins University,Baltimore
More informationSubcortical Structure Segmentation using Probabilistic Atlas Priors
Subcortical Structure Segmentation using Probabilistic Atlas Priors Sylvain Gouttard a, Martin Styner a,b, Sarang Joshi c, Rachel G. Smith a, Heather Cody a, Guido Gerig a,b a Department of Psychiatry,
More informationBrain Portion Peeling from T2 Axial MRI Head Scans using Clustering and Morphological Operation
159 Brain Portion Peeling from T2 Axial MRI Head Scans using Clustering and Morphological Operation K. Somasundaram Image Processing Lab Dept. of Computer Science and Applications Gandhigram Rural Institute
More informationRobust Multimodal Dictionary Learning
Robust Multimodal Dictionary Learning Tian Cao 1, Vladimir Jojic 1, Shannon Modla 3, Debbie Powell 3, Kirk Czymmek 4, and Marc Niethammer 1,2 1 University of North Carolina at Chapel Hill, NC 2 Biomedical
More informationAn Intensity Consistent Approach to the Cross Sectional Analysis of Deformation Tensor Derived Maps of Brain Shape
An Intensity Consistent Approach to the Cross Sectional Analysis of Deformation Tensor Derived Maps of Brain Shape C. Studholme, V. Cardenas, A. Maudsley, and M. Weiner U.C.S.F., Dept of Radiology, VAMC
More informationAppendix E1. Supplementary Methods. MR Image Acquisition. MR Image Analysis
RSNA, 2015 10.1148/radiol.2015150532 Appendix E1 Supplementary Methods MR Image Acquisition By using a 1.5-T system (Avanto, Siemens Medical, Erlangen, Germany) under a program of regular maintenance (no
More informationAn ITK Filter for Bayesian Segmentation: itkbayesianclassifierimagefilter
An ITK Filter for Bayesian Segmentation: itkbayesianclassifierimagefilter John Melonakos 1, Karthik Krishnan 2 and Allen Tannenbaum 1 1 Georgia Institute of Technology, Atlanta GA 30332, USA {jmelonak,
More informationPATCH BASED COUPLED DICTIONARY APPROACH FOR CARDIAC MRI IMAGES USING SR RECONSTRUCTION ALGORITHM
PATCH BASED COUPLED DICTIONARY APPROACH FOR CARDIAC MRI IMAGES USING SR RECONSTRUCTION ALGORITHM G.Priyanka 1, B.Narsimhareddy 2, K.Bhavitha 3, M.Deepika 4,A.Sai Reddy 5 and S.RamaKoteswaraRao 6 1,2,3,4,5
More informationTissue Tracking: Applications for Brain MRI Classification
Tissue Tracking: Applications for Brain MRI Classification John Melonakos a and Yi Gao a and Allen Tannenbaum a a Georgia Institute of Technology, 414 Ferst Dr, Atlanta, GA, USA; ABSTRACT Bayesian classification
More informationAdaptive Dictionary Learning For Competitive Classification Of Multiple Sclerosis Lesions
Adaptive Dictionary Learning For Competitive Classification Of Multiple Sclerosis Lesions Hrishikesh Deshpande, Pierre Maurel, Christian Barillot To cite this version: Hrishikesh Deshpande, Pierre Maurel,
More informationModality Propagation: Coherent Synthesis of Subject-Specific Scans with Data-Driven Regularization
Modality Propagation: Coherent Synthesis of Subject-Specific Scans with Data-Driven Regularization D. Ye 1, D. Zikic 2, B. Glocker 2, A. Criminisi 2, E. Konukoglu 3 1 Department of Radiology, University
More information3D Brain Segmentation Using Active Appearance Models and Local Regressors
3D Brain Segmentation Using Active Appearance Models and Local Regressors K.O. Babalola, T.F. Cootes, C.J. Twining, V. Petrovic, and C.J. Taylor Division of Imaging Science and Biomedical Engineering,
More informationImage Registration + Other Stuff
Image Registration + Other Stuff John Ashburner Pre-processing Overview fmri time-series Motion Correct Anatomical MRI Coregister m11 m 21 m 31 m12 m13 m14 m 22 m 23 m 24 m 32 m 33 m 34 1 Template Estimate
More informationAtlas of Classifiers for Brain MRI Segmentation
Atlas of Classifiers for Brain MRI Segmentation B. Kodner 1,2, S. H. Gordon 1,2, J. Goldberger 3 and T. Riklin Raviv 1,2 1 Department of Electrical and Computer Engineering, 2 The Zlotowski Center for
More informationNeuroImage 83 (2013) Contents lists available at ScienceDirect. NeuroImage. journal homepage:
NeuroImage 83 (2013) 1051 1062 Contents lists available at ScienceDirect NeuroImage journal homepage: www.elsevier.com/locate/ynimg Automatic magnetic resonance spinal cord segmentation with topology constraints
More informationSUPER-RESOLUTION RECONSTRUCTION OF CARDIAC MRI BY USING COUPLED DICTIONARY LEARNING
SUPER-RESOLUTION RECONSTRUCTION OF CARDIAC MRI BY USING COUPLED DICTIONARY LEARNING Gaddala Pratibha (M.Tech.) 1 A. Syam Kumar (Asst.Professor And M.Tech) 2 Nalanda Institute of Engineering and Technology,
More informationComputational Neuroanatomy
Computational Neuroanatomy John Ashburner john@fil.ion.ucl.ac.uk Smoothing Motion Correction Between Modality Co-registration Spatial Normalisation Segmentation Morphometry Overview fmri time-series kernel
More informationStructural Segmentation
Structural Segmentation FAST tissue-type segmentation FIRST sub-cortical structure segmentation FSL-VBM voxelwise grey-matter density analysis SIENA atrophy analysis FAST FMRIB s Automated Segmentation
More informationMEDICAL IMAGE COMPUTING (CAP 5937) LECTURE 4: Pre-Processing Medical Images (II)
SPRING 2016 1 MEDICAL IMAGE COMPUTING (CAP 5937) LECTURE 4: Pre-Processing Medical Images (II) Dr. Ulas Bagci HEC 221, Center for Research in Computer Vision (CRCV), University of Central Florida (UCF),
More informationAN EFFICIENT SKULL STRIPPING ALGORITHM USING CONNECTED REGIONS AND MORPHOLOGICAL OPERATION
AN EFFICIENT SKULL STRIPPING ALGORITHM USING CONNECTED REGIONS AND MORPHOLOGICAL OPERATION Shijin Kumar P. S. 1 and Dharun V. S. 2 1 Department of Electronics and Communication Engineering, Noorul Islam
More informationSurface-based Analysis: Inter-subject Registration and Smoothing
Surface-based Analysis: Inter-subject Registration and Smoothing Outline Exploratory Spatial Analysis Coordinate Systems 3D (Volumetric) 2D (Surface-based) Inter-subject registration Volume-based Surface-based
More informationMRI Segmentation. MRI Bootcamp, 14 th of January J. Miguel Valverde
MRI Segmentation MRI Bootcamp, 14 th of January 2019 Segmentation Segmentation Information Segmentation Algorithms Approach Types of Information Local 4 45 100 110 80 50 76 42 27 186 177 120 167 111 56
More informationVoxel-Wise Displacement as Independent Features in Classification of Multiple Sclerosis
Voxel-Wise Displacement as Independent Features in Classification of Multiple Sclerosis Min Chen 1,2, Aaron Carass 1, Daniel S. Reich 2, Peter A. Calabresi 3, Dzung Pham 4, and Jerry L. Prince 1 1 Image
More informationStructural Segmentation
Structural Segmentation FAST tissue-type segmentation FIRST sub-cortical structure segmentation FSL-VBM voxelwise grey-matter density analysis SIENA atrophy analysis FAST FMRIB s Automated Segmentation
More informationFunctional MRI data preprocessing. Cyril Pernet, PhD
Functional MRI data preprocessing Cyril Pernet, PhD Data have been acquired, what s s next? time No matter the design, multiple volumes (made from multiple slices) have been acquired in time. Before getting
More informationABSTRACT 1. INTRODUCTION 2. METHODS
Finding Seeds for Segmentation Using Statistical Fusion Fangxu Xing *a, Andrew J. Asman b, Jerry L. Prince a,c, Bennett A. Landman b,c,d a Department of Electrical and Computer Engineering, Johns Hopkins
More informationA Generative Model for Image Segmentation Based on Label Fusion Mert R. Sabuncu*, B. T. Thomas Yeo, Koen Van Leemput, Bruce Fischl, and Polina Golland
1714 IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 29, NO. 10, OCTOBER 2010 A Generative Model for Image Segmentation Based on Label Fusion Mert R. Sabuncu*, B. T. Thomas Yeo, Koen Van Leemput, Bruce Fischl,
More informationA Model-Independent, Multi-Image Approach to MR Inhomogeneity Correction
Tina Memo No. 2007-003 Published in Proc. MIUA 2007 A Model-Independent, Multi-Image Approach to MR Inhomogeneity Correction P. A. Bromiley and N.A. Thacker Last updated 13 / 4 / 2007 Imaging Science and
More informationFROM IMAGE RECONSTRUCTION TO CONNECTIVITY ANALYSIS: A JOURNEY THROUGH THE BRAIN'S WIRING. Francesca Pizzorni Ferrarese
FROM IMAGE RECONSTRUCTION TO CONNECTIVITY ANALYSIS: A JOURNEY THROUGH THE BRAIN'S WIRING Francesca Pizzorni Ferrarese Pipeline overview WM and GM Segmentation Registration Data reconstruction Tractography
More informationAttribute Similarity and Mutual-Saliency Weighting for Registration and Label Fusion
Attribute Similarity and Mutual-Saliency Weighting for Registration and Label Fusion Yangming Ou, Jimit Doshi, Guray Erus, and Christos Davatzikos Section of Biomedical Image Analysis (SBIA) Department
More informationMARS: Multiple Atlases Robust Segmentation
Software Release (1.0.1) Last updated: April 30, 2014. MARS: Multiple Atlases Robust Segmentation Guorong Wu, Minjeong Kim, Gerard Sanroma, and Dinggang Shen {grwu, mjkim, gerard_sanroma, dgshen}@med.unc.edu
More informationElastically Deforming a Three-Dimensional Atlas to Match Anatomical Brain Images
University of Pennsylvania ScholarlyCommons Technical Reports (CIS) Department of Computer & Information Science May 1993 Elastically Deforming a Three-Dimensional Atlas to Match Anatomical Brain Images
More informationMagnetic resonance image tissue classification using an automatic method
Yazdani et al. Diagnostic Pathology (2014) 9:207 DOI 10.1186/s13000-014-0207-7 METHODOLOGY Open Access Magnetic resonance image tissue classification using an automatic method Sepideh Yazdani 1, Rubiyah
More informationHistograms. h(r k ) = n k. p(r k )= n k /NM. Histogram: number of times intensity level rk appears in the image
Histograms h(r k ) = n k Histogram: number of times intensity level rk appears in the image p(r k )= n k /NM normalized histogram also a probability of occurence 1 Histogram of Image Intensities Create
More informationAutomatic Subcortical Segmentation Using a Contextual Model
Automatic Subcortical Segmentation Using a Contextual Model Jonathan H. Morra 1, Zhuowen Tu 1, Liana G. Apostolova 1,2, Amity E. Green 1,2, Arthur W. Toga 1, and Paul M. Thompson 1 1 Laboratory of Neuro
More informationSupplementary methods
Supplementary methods This section provides additional technical details on the sample, the applied imaging and analysis steps and methods. Structural imaging Trained radiographers placed all participants
More informationGLIRT: Groupwise and Longitudinal Image Registration Toolbox
Software Release (1.0.1) Last updated: March. 30, 2011. GLIRT: Groupwise and Longitudinal Image Registration Toolbox Guorong Wu 1, Qian Wang 1,2, Hongjun Jia 1, and Dinggang Shen 1 1 Image Display, Enhancement,
More informationThe organization of the human cerebral cortex estimated by intrinsic functional connectivity
1 The organization of the human cerebral cortex estimated by intrinsic functional connectivity Journal: Journal of Neurophysiology Author: B. T. Thomas Yeo, et al Link: https://www.ncbi.nlm.nih.gov/pubmed/21653723
More informationFree-Form B-spline Deformation Model for Groupwise Registration
Free-Form B-spline Deformation Model for Groupwise Registration The Harvard community has made this article openly available. Please share how this access benefits you. Your story matters Citation Balci
More informationTISSUE classification is a necessary step in many medical
IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 18, NO. 9, SEPTEMBER 1999 737 Adaptive Fuzzy Segmentation of Magnetic Resonance Images Dzung L. Pham, Student Member, IEEE, and Jerry L. Prince,* Member, IEEE
More informationFuzzy Multi-channel Clustering with Individualized Spatial Priors for Segmenting Brain Lesions and Infarcts
Fuzzy Multi-channel Clustering with Individualized Spatial Priors for Segmenting Brain Lesions and Infarcts Evangelia Zacharaki, Guray Erus, Anastasios Bezerianos, Christos Davatzikos To cite this version:
More informationSTATISTICAL ATLAS-BASED SUB-VOXEL SEGMENTATION OF 3D BRAIN MRI
STATISTICA ATAS-BASED SUB-VOXE SEGMENTATION OF 3D BRAIN MRI Marcel Bosc 1,2, Fabrice Heitz 1, Jean-Paul Armspach 2 (1) SIIT UMR-7005 CNRS / Strasbourg I University, 67400 Illkirch, France (2) IPB UMR-7004
More informationAtlas Based Segmentation of the prostate in MR images
Atlas Based Segmentation of the prostate in MR images Albert Gubern-Merida and Robert Marti Universitat de Girona, Computer Vision and Robotics Group, Girona, Spain {agubern,marly}@eia.udg.edu Abstract.
More informationComparison Study of Clinical 3D MRI Brain Segmentation Evaluation
Comparison Study of Clinical 3D MRI Brain Segmentation Evaluation Ting Song 1, Elsa D. Angelini 2, Brett D. Mensh 3, Andrew Laine 1 1 Heffner Biomedical Imaging Laboratory Department of Biomedical Engineering,
More informationADAPTIVE GRAPH CUTS WITH TISSUE PRIORS FOR BRAIN MRI SEGMENTATION
ADAPTIVE GRAPH CUTS WITH TISSUE PRIORS FOR BRAIN MRI SEGMENTATION Abstract: MIP Project Report Spring 2013 Gaurav Mittal 201232644 This is a detailed report about the course project, which was to implement
More informationMulti-Sectional Views Textural Based SVM for MS Lesion Segmentation in Multi-Channels MRIs
56 The Open Biomedical Engineering Journal, 2012, 6, 56-72 Open Access Multi-Sectional Views Textural Based SVM for MS Lesion Segmentation in Multi-Channels MRIs Bassem A. Abdullah*, Akmal A. Younis and
More informationNeuroimage Processing
Neuroimage Processing Instructor: Moo K. Chung mkchung@wisc.edu Lecture 2-3. General Linear Models (GLM) Voxel-based Morphometry (VBM) September 11, 2009 What is GLM The general linear model (GLM) is a
More informationLow-Rank to the Rescue Atlas-based Analyses in the Presence of Pathologies
Low-Rank to the Rescue Atlas-based Analyses in the Presence of Pathologies Xiaoxiao Liu 1, Marc Niethammer 2, Roland Kwitt 3, Matthew McCormick 1, and Stephen Aylward 1 1 Kitware Inc., USA 2 University
More information